© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 111921
    Prev
    Next
    INDEX
    Explanations

    food prepared fresh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     食品
    0.40
     수정
    0.39
     탐
    0.38
     식품
    0.38
    윕
    0.38
    mtrl
    0.38
     ڈیٹ
    0.38
    鎭
    0.38
     FOOD
    0.37
    μπο
    0.37
    POSITIVE LOGITS
     freshly
    0.82
     fresh
    0.67
    Fresh
    0.63
     onsite
    0.63
    fresh
    0.62
     frescas
    0.61
     Fresh
    0.59
     freshness
    0.59
     individualized
    0.59
     frisch
    0.58
    Activations Density 0.028%

    No Known Activations